35 citations · 43 across the 7 of their papers we have counts for
7 papers
SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks
Xingning Dong, Qingpei Guo, Tian Gan +5
We present a framework for learning cross-modal video representations by directly pre-training on raw data to facilitate various downstream video-text tasks. Our main contributions…
Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval
Chen Jiang, Kaiming Huang, Sifeng He +9
With the explosive growth of web videos in recent years, large-scale Content-Based Video Retrieval (CBVR) becomes increasingly essential in video filtering, recommendation, and cop…
Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval
Tan Pan, Furong Xu, Xudong Yang +7
Image retrieval plays an important role in the Internet world. Usually, the core parts of mainstream visual retrieval systems include an online service of the embedding model and a…
DC-Former: Diverse and Compact Transformer for Person Re-Identification
Wen Li, Cheng Zou, Meng Wang +5
In person re-identification (re-ID) task, it is still challenging to learn discriminative representation by deep learning, due to limited data. Generally speaking, the model will g…
Solutions for Fine-grained and Long-tailed Snake Species Recognition in SnakeCLEF 2022
Cheng Zou, Furong Xu, Meng Wang +2
Automatic snake species recognition is important because it has vast potential to help lower deaths and disabilities caused by snakebites. We introduce our solution in SnakeCLEF 20…
A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection
Sifeng He, Xudong Yang, Chen Jiang +13
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset. Compared with existing copy detection datasets r…
HBReID: Harder Batch for Re-identification
Wen Li, Furong Xu, Jianan Zhao +4
Triplet loss is a widely adopted loss function in ReID task which pulls the hardest positive pairs close and pushes the hardest negative pairs far away. However, the selected sampl…